Jagmohan Sharma

Writer-independent off-line signature verification using surroundedness feature

The paper presents a novel set of features based on surroundedness property of a signature (image in binary form) for off-line signature verification. The proposed feature set describes the shape of a signature in terms of spatial distribution of black pixels around a candidate pixel (on the signature). It also provides a measure of texture through the correlation among signature pixels in the neighborhood of that candidate pixel. So the proposed feature set is unique in the sense that it contains both shape and texture property unlike most of the earlier proposed features for off-line signature verification. Since the features are proposed based on intuitive idea of the problem, evaluation of features by various feature selection techniques has also been sought to get a compact set of features. To examine the efficacy of the proposed features, two popular classifiers namely, multilayer perceptron and support vector machine are implemented and tested on two publicly available database namely, GPDS300 corpus and CEDAR signature database.

A writer-independent off-line signature verification system based on signature morphology

In this work, we address off-line signature verification as a writer-independent system. We propose a set of morphological features, extracted from off-line signature images. To examine the effectiveness of the features, a publicly available signature database, namely CEDAR signature database is used. A pair of signatures is fed to the system to give an inference for their (dis)similarity. To get a compact set of features, a multilayer perceptron based feature analysis technique is utilized. A 10-fold cross-validation framework based on support vector machine is used for verification. Receiver operator curve (ROC) analysis gives an equal error rate (EER) of 11.59%, which is comparable to the state-of-the-arts reported on this database.

A novel sparse model based forensic writer identification

The paper presents a novel method for writer identification based on sparse representation of handwritten structural primitives, called graphemes or fraglets. The proposed method is different from the existing grapheme based methods as the earlier methods use vector quantization based coding (clustering method) to get a document descriptor, while the proposed method uses sparse coding for the same. Literature shows that the sparse coding outperforms vector quantization in many real life applications including face recognition. Sparse coding can achieve comparatively much lower reconstruction error. Secondly, the sparsity allows representation to be specialized and can capture a writer specific features more accurately. Graphemes (fraglets) extracted from a document are represented in terms of Fourier and wavelet descriptors because the fraglet contour may be well described by its global as well as local characteristics. Wavelet descriptors also give a multi-resolution representation of the shape. Results have shown that even with a smaller codebook (than the earlier reported systems), the proposed method achieves better performance.

Assessing “inherent vulnerability” of forests: a methodological approach and a case study from Western Ghats, India

The objective of this study is to present a methodological approach to assess the inherent vulnerability of forests and apply it to a case study. Addressing inherent vulnerability, resulting from current stresses, is a necessary step for building resilience to long-term climate change. The proposed approach includes use of analytical framework that enables selection of vulnerability criteria and indicators systematically, application of pairwise comparison method (PCM) for assigning weights, and synthesis of a composite vulnerability index. This methodological approach has been applied at local scale to Aduvalli Protected Forest in Western Ghats in South India, where a vulnerability index value of 0.248 is estimated. Results of the case study indicate that ‘preponderance of invasive species’ and forest dependence of community are the major sources of vulnerability at present for Aduvalli Protected Forest. Adoption of this methodology can assist in development of forest management plans to enhance adaptability of Aduvalli PF to current as well as future stresses, including climate change. This methodological approach can be applied across forest-types after appropriate changes to criteria and indicators and their weights, to estimate the inherent vulnerability to enable development of adaptation strategy.

Challenges in vulnerability assessment of forests under climate change

Forest-management goals in the context of climate change are to reduce the adverse impact of climate change on biodiversity, ecosystem services and carbon stocks. For developing an effective adaptation strategy, knowledge on nature and sources of vulnerability of forests is necessary to conserve or enhance carbon sinks. However, assessing the vulnerability of forest ecosystems is a challenging task, as the mechanisms that determine vulnerability cannot be observed directly. In this article, we list the challenges in forest vulnerability assessments and propose an assessment of inherent vulnerability by using process-based indicators under the current climate. We also suggest periodic assessment of vulnerability, which is necessary to review adaptation strategies for the management of forests and forest carbon stocks.

A Novel Approach for Detection of Alteration in Ball Pen Writings

Addition or alteration to documents that have profound implication is very common. The technique that Forensic Document Examiners (FDEs) use for the examination of such documents is basically a physical examination. In this paper we consider the alteration detection as a two-class pattern recognition problem. Image processing techniques are used for feature extraction and a neural network based feature analysis technique is used for finding a set of discriminatory features. The results using a nearest neighbor classifier are very encouraging. The results also demonstrate the effectiveness of feature analysis.

Forensic Detection of Fraudulent Alteration in Ball-Point Pen Strokes

Alteration and addition to valuable data on paper documents are among the fastest growing crimes around the globe. The loss due to these crimes is huge and is increasing with an alarming rate. The techniques, which are used by forensic document examiners, to examine such cases are still limited to manual examination of physical, chemical and microscopic characteristics. Moreover, it is very difficult to detect an alteration when the ink of similar color is involved. We could not find much in the literature to deal with this problem in an automated pattern recognition framework. In this paper, we restrict ourselves to alterations made with ball-point pen strokes and propose a scheme for detection of such alterations using pattern recognition tools. For this, a large set of color and texture based features is extracted. To choose an adequate set of useful features from the extracted ones, a multilayer perceptron (MLP)-based feature analysis technique is used. For detection of the alteration, three different classifiers, namely, K-nearest neighbor, MLP and support vector machines are used. The results are quite promising.

Detection of Fraudulent Alterations in Ball-Point Pen Strokes Using Support Vector Machines

Fraudulent addition to cheques, wills, contracts, and other legal documents may result in serious consequences leading to an irreparable damage in terms of human suffering as well as severe financial loss. The increasing graph of loss due to such a white collar crime is a matter of serious concern. In this paper we propose a mechanism for detection of alteration in ball-point pen strokes using pattern recognition techniques. A large set of features based on color and texture is extracted from images of documents. To find a set of discriminatory features, a neural-network-based feature analysis technique is used. Finally, Support Vector Machine (SVM) is used for the detection. The model selection is done using cross-validation in conjunction with some constraint on false positive rate (FPR) that is demanded by the problem domain. The results are very encouraging.

Predicting Energy Requirement for Cooling the Building Using Artificial Neural Network

This paper explores total cooling load during summers and total carbon emissions of a six storey building by using artificial neural network (ANN). Parameters used for the calculation were conduction losses, ventilation losses, solar heat gain and internal gain. The standard back-propagation learning algorithm has been used in the network. The energy performance in buildings is influenced by many factors, such as ambient weather conditions, building structure and characteristics, the operation of sub-level components like lighting and HVAC systems, occupancy and their behavior. This complex situation makes it very difficult to accurately implement the prediction of building energy consumption. The calculated cooling load was 0.87 million kW per year. ANN application showed that data was best fit for the regression coefficient of 0.9955 with best validation performance of 0.41231 in case of conduction losses. To meet out this energy demand various fuel options are presented along with their cost and carbon emission.

Impact of Climate Change on Vegetation Distribution and Net Primary Productivity of Forests of Himalayan River Basins: Brahmaputra, Koshi and Indus

The impacts of climate change in terms of forest vegetation shifts and Net Primary Productivity (NPP) changes are assessed for Brahmaputra, Koshi and Indus river basins for the mid (2021-2050) and long (2071-2100) terms for RCP4.5 and RCP8.5 scenarios. Two Dynamical Global Vegetation Models (DGVMs), Integrated BIosphere Simulator (IBIS) and (Lund Postdam and Jena (LPJ), have been used for this purpose. The DGVMs are driven by the ensemble mean climate projections from 5 climate models that contributed to the CMIP5 data base. While both DGVMs project vegetation shifts in the forest areas of the basins, there are large differences in vegetation shifts projected by IBIS and LPJ. This may be attributed to differing representation of land surface processes and to differences in the number of vegetation types (Plant Functional Types) defined and simulated in the two models. However, there is some agreement in NPP changes as projected by both IBIS and LPJ, with IBIS mostly projecting a larger increase in NPP for the future scenarios. Despite the uncertainties with respect to climate change projections at river basin level and the differing impact assessments from different DGVMs, it is necessary to assess the “vulnerability” of the forest ecosystems and forest dependent communities to current climate risks and future climate change and to develop and implement resilience or adaptation measures. Assessment of the “vulnerability” and designing of the adaptation strategies could be undertaken for all the forested grids where both IBIS and LPJ project vegetation shifts.